
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
import numpy as np


pd.options.display.float_format = '{:,.2f}'.format


df_apps = pd.read_csv('apps.csv')


df_apps.shape

(10841, 12)


df_apps.columns

Index(['App', 'Category', 'Rating', 'Reviews', 'Size_MBs', 'Installs', 'Type',
       'Price', 'Content_Rating', 'Genres', 'Last_Updated', 'Android_Ver'],
      dtype='object')


df_apps.sample(5)


df_apps_new = df_apps.drop(columns=["Last_Updated", "Android_Ver"])


df_apps_new.Rating.isna().sum()

1474


df_apps_new[df_apps_new["Rating"].isna() == True]


df_apps_clean = df_apps_new.dropna()
df_apps_clean.sample(5)


df_apps_clean.duplicated().sum()

476


df_apps_clean = df_apps_clean.drop_duplicates(subset=["App","Type","Price"])
df_apps_clean.shape

(8199, 10)


df_apps_clean_manyreviews = df_apps_clean[df_apps_clean["Reviews"] > 100]
df_apps_clean_manyreviews.sort_values(by="Rating", ascending=False).head(10)


df_apps_clean.sort_values(by="Size_MBs", ascending=False).head()


df_apps_clean.sort_values(by="Reviews", ascending=False).head(5)


ratings = df_apps_clean.Content_Rating.value_counts()
ratings

Everyone           6621
Teen                912
Mature 17+          357
Everyone 10+        305
Adults only 18+       3
Unrated               1
Name: Content_Rating, dtype: int64


fig = px.pie(labels=ratings.index,
values=ratings.values,
title="Content Rating Distribution",
names=ratings.index,
hole=0.6)
fig.update_traces(textposition='outside', textinfo='percent+label')
 
fig.show()


df_apps_clean.dtypes

App                object
Category           object
Rating            float64
Reviews             int64
Size_MBs          float64
Installs           object
Type               object
Price              object
Content_Rating     object
Genres             object
dtype: object


df_apps_clean.Installs.value_counts()

1,000,000        1417
100,000          1096
10,000            988
10,000,000        933
1,000             698
5,000,000         607
500,000           504
50,000            457
5,000             425
100               303
50,000,000        202
500               199
100,000,000       189
10                 69
50                 56
500,000,000        24
1,000,000,000      20
5                   9
1                   3
Name: Installs, dtype: int64


df_apps_clean.Installs = df_apps_clean.Installs.str.replace(',', '')
df_apps_clean.Installs = pd.to_numeric(df_apps_clean.Installs)


df_apps_clean[['App', 'Installs']].groupby('Installs').count()


df_apps_clean["Price"].head()

21        0
28    $1.49
47    $0.99
82        0
99        0
Name: Price, dtype: object


df_apps_clean.Price = df_apps_clean.Price.str.replace('$', '', regex=True)
df_apps_clean.Price = pd.to_numeric(df_apps_clean.Price)


df_apps_clean.sort_values(by="Price",ascending=False).head(20)


indexOverprices = df_apps_clean[df_apps_clean.Price > 250].index
df_apps_clean.drop(indexOverprices, inplace=True)


df_apps_clean.sort_values(by="Price",ascending=False).head(20)


gross_revenue = df_apps_clean.Installs * df_apps_clean.Price
df_apps_clean.insert(9, 'Revenue_Estimate', gross_revenue)


df_apps_clean.sort_values(by="Revenue_Estimate",ascending=False).head(10)


df_apps_clean.Category.nunique()

33


top10_category = df_apps_clean.Category.value_counts().head(10)
bar = px.bar(x = top10_category.index, 
             y = top10_category.values,
             labels={'x':'Category', 'y':'Number of Apps'},
             title = "Highest Competition in terms of Number of Apps")
bar.show()


category_installs = df_apps_clean.groupby('Category').agg({'Installs': pd.Series.sum})
category_installs.sort_values('Installs', ascending=True, inplace=True)


h_bar = px.bar(x = category_installs.Installs,
               y = category_installs.index,
               orientation='h',
               title='Category Popularity in terms of Number of Downloads')
 
h_bar.update_layout(xaxis_title='Number of Downloads', yaxis_title='Category')
h_bar.show()


cat_number = df_apps_clean.groupby('Category').agg({'App': pd.Series.count})


cat_merged_df = pd.merge(cat_number, category_installs, on='Category', how="inner")
print(f'The dimensions of the DataFrame are: {cat_merged_df.shape}')
cat_merged_df.sort_values('Installs', ascending=False).head()

The dimensions of the DataFrame are: (33, 2)


scatter = px.scatter(cat_merged_df, 
                    x='App',
                    y='Installs',
                    title='Category Concentration',
                    size='App',
                    hover_name=cat_merged_df.index,
                    color='Installs')
 
scatter.update_layout(xaxis_title="Number of Apps (Lower=More Concentrated)",
                      yaxis_title="Installs",
                      yaxis=dict(type='log'))
 
scatter.show()


df_apps_clean.Genres.nunique()

114


df_apps_clean.Genres.value_counts()

Tools                         718
Entertainment                 467
Education                     429
Productivity                  301
Personalization               298
                             ... 
Lifestyle;Education             1
Health & Fitness;Education      1
Arcade;Pretend Play             1
Tools;Education                 1
Board;Pretend Play              1
Name: Genres, Length: 114, dtype: int64


reretest = df_apps_clean.Genres.str.split(pat=";",expand=True)


final_test = reretest.stack()


final_genre = final_test.value_counts()


final_genre.shape

(53,)


genre_bar = px.bar(x=final_genre.index[:15], y=final_genre[:15],title='Top Genres',labels={'x':'Genre', 'y':'Number of Apps'},color=final_genre[:15],color_continuous_scale="Agsunset")
genre_bar.update_layout(coloraxis_showscale=False)
genre_bar.show()


df_apps_free = df_apps_clean[df_apps_clean.Type == "Free"]
df_apps_paid = df_apps_clean[df_apps_clean.Type == "Paid"]


df_free = df_apps_free.groupby('Category').agg({'Type': pd.Series.count})
df_paid = df_apps_paid.groupby('Category').agg({'Type': pd.Series.count})
df_merged = pd.merge(df_free, df_paid, on='Category', how="left")


df_merged.rename(columns={"Type_x": "Free", "Type_y": "Paid"},inplace=True)
df_merged.fillna(0, inplace=True)


fig = go.Figure()

fig.add_trace(go.Bar(
  x = df_merged.index,
  y = df_merged.Free,
  name = "Free Apps",
))

fig.add_trace(go.Bar(
  x = df_merged.index,
  y = df_merged.Paid,
  name = "Paid Apps",
))

fig.update_layout(title="Free vs Paid apps by Category",xaxis_title="Category",
                      yaxis_title="Number of Apps",
                      yaxis=dict(type='log'))

fig.update_xaxes(categoryorder='total descending')

fig.show()


df_apps_free.Installs.value_counts()

1000000       1397
100000        1014
10000000       931
10000          871
5000000        607
1000           567
500000         493
50000          417
5000           360
100            237
50000000       202
100000000      189
500            163
10              51
50              42
500000000       24
1000000000      20
5                9
1                1
Name: Installs, dtype: int64


df = df_apps_clean
fig = px.box(df, x="Type", y=df_apps_clean.Installs, points="all",color="Type",notched=True)
fig.update_layout(title="Number of Downloads for Free Apps vs Paid Apps",yaxis=dict(type='log'))
fig.show()


df = df_apps_paid
fig = px.box(df, x="Category", y="Revenue_Estimate")
fig.update_layout(title="Paid Apps Turnover Estimate",yaxis_title="Paid Apps Revenue",yaxis=dict(type='log'))
fig.update_xaxes(categoryorder='min ascending')
fig.show()


df_apps_paid.Price.median()

2.99


df = df_apps_paid
fig = px.box(df, x="Category", y="Price")
fig.update_layout(title="Paid Apps Prices",yaxis_title="Price",yaxis=dict(type='log'))
fig.update_xaxes(categoryorder='max descending')
fig.show()

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Content_Rating	Genres	Last_Updated	Android_Ver
3743	哈哈姆特不EY	COMMUNICATION	NaN	239	18.00	10,000	Free	Everyone	Communication	July 31, 2018	4.4 and up
5397	BEBONCOOL GAMEPAD V1.0	GAME	3.90	404	2.20	100,000	Free	Everyone	Arcade	August 30, 2017	4.0 and up
7046	Yandex.Shell (Launcher+Dialer)	PERSONALIZATION	4.40	87300	6.15	1,000,000	Free	Everyone	Personalization	March 17, 2015	Varies with device
5116	Weather From DMI/YR	WEATHER	4.30	2143	4.75	100,000	Free	Everyone	Weather	July 31, 2018	Varies with device
6965	CppDroid - C/C++ IDE	FAMILY	4.10	29978	19.00	1,000,000	Free	Everyone	Education	August 17, 2017	Varies with device

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Price	Content_Rating	Genres
0	Ak Parti Yardım Toplama	SOCIAL	NaN	0	8.70	0	Paid	$13.99	Teen	Social
1	Ain Arabic Kids Alif Ba ta	FAMILY	NaN	0	33.00	0	Paid	$2.99	Everyone	Education
2	Popsicle Launcher for Android P 9.0 launcher	PERSONALIZATION	NaN	0	5.50	0	Paid	$1.49	Everyone	Personalization
3	Command & Conquer: Rivals	FAMILY	NaN	0	19.00	0	NaN	0	Everyone 10+	Strategy
4	CX Network	BUSINESS	NaN	0	10.00	0	Free	0	Everyone	Business
...	...	...	...	...	...	...	...	...	...	...
5840	Em Fuga Brasil	FAMILY	NaN	1317	60.00	100,000	Free	0	Everyone	Simulation
5862	Voice Tables - no internet	PARENTING	NaN	970	71.00	100,000	Free	0	Everyone	Parenting
6141	Young Speeches	LIBRARIES_AND_DEMO	NaN	2221	2.40	500,000	Free	0	Everyone	Libraries & Demo
7035	SD card backup	TOOLS	NaN	142	3.40	1,000,000	Free	0	Everyone	Tools
7175	Android TV Remote Service	TOOLS	NaN	1	3.70	1,000,000	Free	0	Everyone	Tools

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Price	Content_Rating	Genres
4143	Blue CareOnDemand	MEDICAL	4.40	163	40.00	10,000	Free	0	Everyone	Medical
6518	Elmo Calls by Sesame Street	FAMILY	3.90	6903	25.00	1,000,000	Free	0	Everyone	Educational;Pretend Play
5598	Lapse It • Time Lapse • Pro	PHOTOGRAPHY	4.30	12865	6.90	100,000	Paid	$2.99	Everyone	Photography
8762	iHoroscope - 2018 Daily Horoscope & Astrology	LIFESTYLE	4.50	398307	19.00	10,000,000	Free	0	Everyone	Lifestyle
9742	Five Nights at Freddy's 3 Demo	GAME	4.50	1041836	50.00	10,000,000	Free	0	Teen	Action

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Price	Content_Rating	Genres
3115	Oración CX	LIFESTYLE	5.00	103	3.80	5,000	Free	0	Everyone	Lifestyle
2095	Ríos de Fe	LIFESTYLE	5.00	141	15.00	1,000	Free	0	Everyone	Lifestyle
2438	FD Calculator (EMI, SIP, RD & Loan Eligilibility)	FINANCE	5.00	104	2.30	1,000	Free	0	Everyone	Finance
4791	Tickets SDA 2018 and Exam from the State Traff...	AUTO_AND_VEHICLES	4.90	10479	33.00	100,000	Free	0	Everyone	Auto & Vehicles
2650	DC Comics Amino	SOCIAL	4.90	117	63.00	1,000	Free	0	Teen	Social
4903	CDL Practice Test 2018 Edition	AUTO_AND_VEHICLES	4.90	7774	17.00	100,000	Free	0	Everyone	Auto & Vehicles
2996	H*nest Meditation	LIFESTYLE	4.90	145	48.00	5,000	Paid	$1.99	Mature 17+	Lifestyle
6476	ipsy: Makeup, Beauty, and Tips	BEAUTY	4.90	49790	14.00	1,000,000	Free	0	Everyone	Beauty
3419	DQSalmaan - A fan made App	FAMILY	4.90	707	6.00	10,000	Free	0	Everyone	Entertainment
7127	StrongLifts 5x5 Workout Gym Log & Personal Tra...	HEALTH_AND_FITNESS	4.90	66791	10.00	1,000,000	Free	0	Everyone	Health & Fitness

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Content_Rating	Genres
9942	Talking Babsy Baby: Baby Games	LIFESTYLE	4.00	140995	100.00	10,000,000	Free	Everyone	Lifestyle;Pretend Play
10687	Hungry Shark Evolution	GAME	4.50	6074334	100.00	100,000,000	Free	Teen	Arcade
9943	Miami crime simulator	GAME	4.00	254518	100.00	10,000,000	Free	Mature 17+	Action
9944	Gangster Town: Vice District	FAMILY	4.30	65146	100.00	10,000,000	Free	Mature 17+	Simulation
3144	Vi Trainer	HEALTH_AND_FITNESS	3.60	124	100.00	5,000	Free	Everyone	Health & Fitness

Introduction¶

About the Dataset of Google Play Store Apps & Reviews¶

Notebook Presentation¶

Data Cleaning¶

Drop Unused Columns¶

Remove NaN values in Ratings¶

Find and Remove Duplicates¶

Highest Rated Apps¶

Largest Apps in terms of Size (MBs)¶

Apps with Most Reviews¶

Plotly Pie and Donut Charts - Visualise Categorical Data: Content Ratings¶

Numeric Type Conversion¶

Most Expensive Apps and (Rough) Sales Revenue Estimate¶

Most expensive apps¶

Remove overpriced apps¶

Highest Grossing Paid Apps¶

Analysis of App Categories¶

Vertical Bar Chart - Highest Competition (Number of Apps)¶

Horizontal Bar Chart - Most Popular Categories (Highest Downloads)¶

Category Concentration - Downloads vs. Competition¶

Colour Scales in Plotly Charts - Competition in Genres¶

Grouped Bar Charts: Free vs. Paid Apps per Category¶

Number of downloads : Free apps vs. Paid apps¶

Plotly Box Plots: Paid Apps Turnover estimates¶

Paid Apps Pricing Strategy per category¶

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Content_Rating	Genres
10805	Facebook	SOCIAL	4.10	78158306	5.30	1,000,000,000	Free	Teen	Social
10785	WhatsApp Messenger	COMMUNICATION	4.40	69119316	3.50	1,000,000,000	Free	Everyone	Communication
10806	Instagram	SOCIAL	4.50	66577313	5.30	1,000,000,000	Free	Teen	Social
10784	Messenger – Text and Video Chat for Free	COMMUNICATION	4.00	56642847	3.50	1,000,000,000	Free	Everyone	Communication
10650	Clash of Clans	GAME	4.60	44891723	98.00	100,000,000	Free	Everyone 10+	Strategy

	App
Installs
1	3
5	9
10	69
50	56
100	303
500	199
1000	698
5000	425
10000	988
50000	457
100000	1096
500000	504
1000000	1417
5000000	607
10000000	933
50000000	202
100000000	189
500000000	24
1000000000	20

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Price	Content_Rating	Genres
3946	I'm Rich - Trump Edition	LIFESTYLE	3.60	275	7.30	10000	Paid	400.00	Everyone	Lifestyle
2461	I AM RICH PRO PLUS	FINANCE	4.00	36	41.00	1000	Paid	399.99	Everyone	Finance
4606	I Am Rich Premium	FINANCE	4.10	1867	4.70	50000	Paid	399.99	Everyone	Finance
3145	I am rich(premium)	FINANCE	3.50	472	0.94	5000	Paid	399.99	Everyone	Finance
3554	💎 I'm rich	LIFESTYLE	3.80	718	26.00	10000	Paid	399.99	Everyone	Lifestyle
5765	I am rich	LIFESTYLE	3.80	3547	1.80	100000	Paid	399.99	Everyone	Lifestyle
1946	I am rich (Most expensive app)	FINANCE	4.10	129	2.70	1000	Paid	399.99	Teen	Finance
2775	I Am Rich Pro	FAMILY	4.40	201	2.70	5000	Paid	399.99	Everyone	Entertainment
3221	I am Rich Plus	FAMILY	4.00	856	8.70	10000	Paid	399.99	Everyone	Entertainment
3114	I am Rich	FINANCE	4.30	180	3.80	5000	Paid	399.99	Everyone	Finance
1331	most expensive app (H)	FAMILY	4.30	6	1.50	100	Paid	399.99	Everyone	Entertainment
2394	I am Rich!	FINANCE	3.80	93	22.00	1000	Paid	399.99	Everyone	Finance
3897	I Am Rich	FAMILY	3.60	217	4.90	10000	Paid	389.99	Everyone	Entertainment
2193	I am extremely Rich	LIFESTYLE	2.90	41	2.90	1000	Paid	379.99	Everyone	Lifestyle
3856	I am rich VIP	LIFESTYLE	3.80	411	2.60	10000	Paid	299.99	Everyone	Lifestyle
2281	Vargo Anesthesia Mega App	MEDICAL	4.60	92	32.00	1000	Paid	79.99	Everyone	Medical
1407	LTC AS Legal	MEDICAL	4.00	6	1.30	100	Paid	39.99	Everyone	Medical
2629	I am Rich Person	LIFESTYLE	4.20	134	1.80	1000	Paid	37.99	Everyone	Lifestyle
2481	A Manual of Acupuncture	MEDICAL	3.50	214	68.00	1000	Paid	33.99	Everyone	Medical
4264	Golfshot Plus: Golf GPS	SPORTS	4.10	3387	25.00	50000	Paid	29.99	Everyone	Sports

	App	Category	Rating	Reviews	Size_MBs	Installs	Type	Price	Content_Rating	Revenue_Estimate	Genres
9220	Minecraft	FAMILY	4.50	2376564	19.00	10000000	Paid	6.99	Everyone 10+	69,900,000.00	Arcade;Action & Adventure
8825	Hitman Sniper	GAME	4.60	408292	29.00	10000000	Paid	0.99	Mature 17+	9,900,000.00	Action
7151	Grand Theft Auto: San Andreas	GAME	4.40	348962	26.00	1000000	Paid	6.99	Mature 17+	6,990,000.00	Action
7477	Facetune - For Free	PHOTOGRAPHY	4.40	49553	48.00	1000000	Paid	5.99	Everyone	5,990,000.00	Photography
7977	Sleep as Android Unlock	LIFESTYLE	4.50	23966	0.85	1000000	Paid	5.99	Everyone	5,990,000.00	Lifestyle
6594	DraStic DS Emulator	GAME	4.60	87766	12.00	1000000	Paid	4.99	Everyone	4,990,000.00	Action
6082	Weather Live	WEATHER	4.50	76593	4.75	500000	Paid	5.99	Everyone	2,995,000.00	Weather
7954	Bloons TD 5	FAMILY	4.60	190086	94.00	1000000	Paid	2.99	Everyone	2,990,000.00	Strategy
7633	Five Nights at Freddy's	GAME	4.60	100805	50.00	1000000	Paid	2.99	Teen	2,990,000.00	Action
6746	Card Wars - Adventure Time	FAMILY	4.30	129603	23.00	1000000	Paid	2.99	Everyone 10+	2,990,000.00	Card;Action & Adventure

	App	Installs
Category
GAME	910	13858762717
COMMUNICATION	257	11039241530
TOOLS	719	8099724500
PRODUCTIVITY	301	5788070180
SOCIAL	203	5487841475